{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:54IYG2P7FJA7W4ENZ253NOJPRX","short_pith_number":"pith:54IYG2P7","schema_version":"1.0","canonical_sha256":"ef118369ff2a41fb708dcebbb6b92f8dcaf8d16261744b2cbee715ee67f61d19","source":{"kind":"arxiv","id":"2502.05232","version":1},"attestation_state":"computed","paper":{"title":"Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Adam Stooke, Khe Chai Sim, Pedro Moreno Mengibar, Rohit Prabhavalkar","submitted_at":"2025-02-06T22:09:52Z","abstract_excerpt":"Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into the embedding; alignment to the final text output is processed during decoding. We discover that the transformer-based encoder adopted in recent years is actually capable of performing the alignment internally during the forward pass, prior to decoding. This new phenomenon enables a simpler and more efficient model, the \"Aligner-Encoder\". To train it, we di"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.05232","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-06T22:09:52Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"a437dcdb048e2ae3606642ff8a3c76ac29ac0d96507f83b4aeb066deda420a83","abstract_canon_sha256":"4b8e7972a3919ffd07698a7dbfb62f2105b5071ab83eccbaa649ff30aa066365"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:34.545381Z","signature_b64":"v3+oo2cN1rgw3SuYlxgP6RWSaq0a/a2Rm3wzkdLCClvtiZZTjaitZ593yRuepjiwhYSbJBNHctUvtxGp7H3xDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef118369ff2a41fb708dcebbb6b92f8dcaf8d16261744b2cbee715ee67f61d19","last_reissued_at":"2026-07-05T10:11:34.544902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:34.544902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Adam Stooke, Khe Chai Sim, Pedro Moreno Mengibar, Rohit Prabhavalkar","submitted_at":"2025-02-06T22:09:52Z","abstract_excerpt":"Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into the embedding; alignment to the final text output is processed during decoding. We discover that the transformer-based encoder adopted in recent years is actually capable of performing the alignment internally during the forward pass, prior to decoding. This new phenomenon enables a simpler and more efficient model, the \"Aligner-Encoder\". To train it, we di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05232","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.05232/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.05232","created_at":"2026-07-05T10:11:34.544960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05232v1","created_at":"2026-07-05T10:11:34.544960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05232","created_at":"2026-07-05T10:11:34.544960+00:00"},{"alias_kind":"pith_short_12","alias_value":"54IYG2P7FJA7","created_at":"2026-07-05T10:11:34.544960+00:00"},{"alias_kind":"pith_short_16","alias_value":"54IYG2P7FJA7W4EN","created_at":"2026-07-05T10:11:34.544960+00:00"},{"alias_kind":"pith_short_8","alias_value":"54IYG2P7","created_at":"2026-07-05T10:11:34.544960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54IYG2P7FJA7W4ENZ253NOJPRX","json":"https://pith.science/pith/54IYG2P7FJA7W4ENZ253NOJPRX.json","graph_json":"https://pith.science/api/pith-number/54IYG2P7FJA7W4ENZ253NOJPRX/graph.json","events_json":"https://pith.science/api/pith-number/54IYG2P7FJA7W4ENZ253NOJPRX/events.json","paper":"https://pith.science/paper/54IYG2P7"},"agent_actions":{"view_html":"https://pith.science/pith/54IYG2P7FJA7W4ENZ253NOJPRX","download_json":"https://pith.science/pith/54IYG2P7FJA7W4ENZ253NOJPRX.json","view_paper":"https://pith.science/paper/54IYG2P7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05232&json=true","fetch_graph":"https://pith.science/api/pith-number/54IYG2P7FJA7W4ENZ253NOJPRX/graph.json","fetch_events":"https://pith.science/api/pith-number/54IYG2P7FJA7W4ENZ253NOJPRX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54IYG2P7FJA7W4ENZ253NOJPRX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54IYG2P7FJA7W4ENZ253NOJPRX/action/storage_attestation","attest_author":"https://pith.science/pith/54IYG2P7FJA7W4ENZ253NOJPRX/action/author_attestation","sign_citation":"https://pith.science/pith/54IYG2P7FJA7W4ENZ253NOJPRX/action/citation_signature","submit_replication":"https://pith.science/pith/54IYG2P7FJA7W4ENZ253NOJPRX/action/replication_record"}},"created_at":"2026-07-05T10:11:34.544960+00:00","updated_at":"2026-07-05T10:11:34.544960+00:00"}